Lane-change intention prediction is safety-critical for autonomous driving and ADAS, but remains difficult in naturalistic traffic due to noisy kinematics, severe class imbalance, and limited generalization across heterogeneous highway scenarios. We propose Temporal Physics-Informed AI (TPI-AI), a hybrid framework that fuses deep temporal representations with physics-inspired interaction cues. A two-layer bidirectional LSTM (Bi-LSTM) encoder learns compact embeddings from multi-step trajectory histories; we concatenate these embeddings with kinematics-, safety-, and interaction-aware features (e.g., headway, TTC, and safe-gap indicators) and train a LightGBM classifier for three-class intention recognition (No-LC, Left-LC, Right-LC). To improve minority-class reliability, we apply imbalance-aware optimization including resampling/weighting and fold-wise threshold calibration. Experiments on two large-scale drone-based datasets, highD (straight highways) and exiD (ramp-rich environments), use location-based splits and evaluate prediction horizons T = 1, 2, 3 s. TPI-AI outperforms standalone LightGBM and Bi-LSTM baselines, achieving macro-F1 of 0.9562, 0.9124, 0.8345 on highD and 0.9247, 0.8197, 0.7605 on exiD at T = 1, 2, 3 s, respectively. These results show that combining physics-informed interaction features with learned temporal embeddings yields robust multi-scenario lane-change intention prediction.

翻译：换道意图预测对自动驾驶和高级驾驶辅助系统至关重要，但受限于自然交通流中的运动学噪声、严重的类别不平衡以及异构高速公路场景间有限的泛化能力，该任务仍具挑战性。本文提出时序物理信息人工智能框架，该混合框架将深度时序表征与物理启发的交互特征相融合。一个双层双向长短期记忆网络编码器从多步轨迹历史中学习紧凑嵌入表示；我们将这些嵌入与运动学特征、安全性特征及交互感知特征（如车头时距、碰撞时间及安全间隙指标）进行拼接，并训练LightGBM分类器进行三类意图识别（不换道、左换道、右换道）。为提升少数类别的预测可靠性，我们采用包含重采样/加权处理与分折式阈值校准的不平衡感知优化策略。在两个基于无人机采集的大规模数据集（直线高速公路场景的highD数据集与匝道密集场景的exiD数据集）上进行实验，采用基于位置的划分方式，并评估T = 1、2、3秒的预测时域。时序物理信息人工智能框架在各项指标上均优于独立的LightGBM和双向长短期记忆网络基线模型，在highD数据集上T = 1、2、3秒的宏平均F1分数分别达到0.9562、0.9124、0.8345，在exiD数据集上分别达到0.9247、0.8197、0.7605。实验结果表明，融合物理信息交互特征与学习得到的时序嵌入表征能够实现鲁棒的多场景换道意图预测。